AI and machine learning · Free · ₹0
Deep Learning with TensorFlow and Keras
Neural networks for the data a forest cannot read: images of surfaces and windows of vibration. Neurons, loss and gradient descent in plain words, Keras models, training well, data pipelines, CNNs, augmentation and transfer learning, sequence models, evaluation and explanation, and deployment to TensorFlow Lite — all on Colab's free GPU.
Inside the course
From the lessons
What a neural network is, and why now
codebasics
How it learns: gradient descent and backpropagation
codebasics
Training well: dropout, early stopping, imbalance
codebasics
Convolutional networks
codebasics
Sequences: 1-D CNNs, RNNs, LSTMs and autoencoders
codebasics
Saving, TensorFlow Lite and the edge
codebasics
Lesson frames belong to the creators named in the Credits below and are shown from YouTube.
What you will learn
Explain what a network learns and when to use one; pair activations with losses; build, train and regularise Keras models; feed images and signal windows through tf.data; train CNNs and use transfer learning on small datasets; use 1-D CNNs, LSTMs and autoencoders on sensor windows; evaluate with per-class recall and Grad-CAM; export to TensorFlow Lite and measure latency.
- Say when a neural network beats a random forest, and when it does not
- Build and train a Keras model with the right loss, early stopping and dropout, and read its curves
- Feed images from folders and signal windows from streams through a fast tf.data pipeline
- Train a CNN on surface defects and lift it with augmentation and transfer learning
- Classify vibration windows with a 1-D CNN and score anomalies with an autoencoder
- Report per-class recall, explain a prediction with Grad-CAM and export to TensorFlow Lite
Course content
13 modules · 41 lessons · 21h 26m
In order, at whatever pace suits you. Each module ends with a practice task that builds on the last, and a short quiz.
- 01What a neural network is, and why now4 lessons1h 46m
- 02The neuron, activation and loss3 lessons58m
- 03How it learns: gradient descent and backpropagation5 lessons1h 58m
- 04Keras Sequential: your first model3 lessons8h 9m
- 05Training well: dropout, early stopping, imbalance3 lessons1h 9m
- 06Data pipelines: tf.data for images and windows2 lessons60m
- 07Convolutional networks4 lessons1h 8m
- 08Augmentation and transfer learning3 lessons1h 10m
- 09Sequences: 1-D CNNs, RNNs, LSTMs and autoencoders5 lessons55m
- 10Evaluating and explaining a deep model2 lessons39m
- 11Saving, TensorFlow Lite and the edge3 lessons46m
- 12The project: surface defects end to end4 lessons1h 47m
- 13Final assessment0 lessons0m
Requirements
- Who it is for
- Intermediate. Needs the Machine Learning with Python course, or equivalent: train/test discipline, metrics, Pandas.
- Software
- Google Colab with a free GPU runtime. TensorFlow and Keras are pre-installed.
- Hardware
- None. A Raspberry Pi is optional for the deployment module.
Deep Learning with TensorFlow and Keras at a glance
Deep Learning with TensorFlow and Keras is a free, self-paced online ai and machine learning course from EDWartens India with 13 modules, 21h 26m of video lessons, written notes, practice tasks and assessments, and an optional verifiable certificate.
- Price
- ₹0, free for good. No trial, no card. Comparable classroom training of this length costs about ₹11,999.
- Format
- 13 self-paced modules, 21h 26m of video, written notes, a quiz per module and a final assessment.
- Level
- Intermediate. Intermediate. Needs the Machine Learning with Python course, or equivalent: train/test discipline, metrics, Pandas.
- Brand
- Vendor-neutral
- Software
- Google Colab with a free GPU runtime. TensorFlow and Keras are pre-installed.
- Hardware
- None. A Raspberry Pi is optional for the deployment module.
- Certificate
- Optional EDWartens Certificate of Completion, verifiable by code. Not a vendor credential.
- Video lessons by
- codebasics, freeCodeCamp.org, Edje Electronics (independent creators, credited below)
- Language
- English
A shareable EDWartens certificate
Finish every module and pass the final assessment, and the optional EDWartens certificate is yours. It carries a unique verification code on a public page anyone can check, so it stands up when a recruiter looks it up. See it below.
- Add it to your LinkedIn profile in one click
- Link it from a CV or portfolio, the URL is permanent
- Publicly verifiable by code, not a PDF anyone can edit
- Issued by EDWartens India, the training centre itself
The course itself stays free whether or not you ever buy one.
Stuck? Ask a practising engineer
A free course usually means a comment section and hope. This one does not. Every module has an Ask-your-trainer panel that reaches the same engineers who teach our paid programme: people who commission panels for a living, not moderators.
- Questions answered in the context of the module you are on
- The same engineers who teach the AEP programme
- Career tools, CV help and public job listings included
- Your progress and notes stay in your account for good
Pairs well with
PLC programming · FreeSiemens TIA PortalFrom zero electrical knowledge to a working, simulated S7-1200 program, for nothing.
PLC programming · FreeSiemens S7-1200 with TIA Portal: The Tutorial SeriesEvery S7-1200 instruction, one short video at a time: bits, edges, timers, counters, comparators, maths, MOVE, conversion, analog scaling, jumps and shift registers.
HMI · FreeSiemens TIA Portal HMI: KTP and Comfort Panels with WinCCEvery screen a plant operator touches, built in TIA Portal: tags, buttons, symbols, numeric input, bar graphs, navigation and templates, trends, alarms, recipes, faceplates, pop-ups, users and languages.
Process control · FreeSiemens TIA Portal PID Compact and Analog ProcessingClosed-loop control the way it is done on an S7-1200 or S7-1500: analog in, NORM_X and SCALE_X, PID_Compact configured, tuned and wired to an HMI, analog or PWM out, proved on a free tank simulation.Learning paths with this course
- Applied AI engineer · 4 coursesThe four skills AI job posts name most: machine learning with scikit-learn, computer vision with OpenCV, deep learning with TensorFlow and Keras, and RAG chatbots with LangChain — each with a plant project.
Learner reviews
No reviews yet
Reviews here are written only by learners who have finished every module of Deep Learning with TensorFlow and Keras, and they are published exactly as written. Finish the course and yours will be the first.
Common questions
Do I need a GPU?
Google Colab gives you one free; every model in the course trains in minutes on it. Set the runtime type to GPU in the first cell of each notebook.
How much maths?
You see gradient descent and backpropagation once, in twenty lines of NumPy, so you know what the framework does. After that Keras does the calculus and you do the engineering. Nothing in the assessments asks for derivatives.
What are the projects?
A surface-defect classifier on 1,200 images — baseline CNN, augmentation and transfer learning compared on one sealed test set with per-class recall, Grad-CAM and a TensorFlow Lite export — and a vibration-window classifier comparing a 1-D CNN with an LSTM, plus an autoencoder anomaly score trained on healthy data only.
Should I do this before or after the OpenCV course?
After, ideally: the OpenCV course teaches you what a convolution filter is by making you tune one by hand, and it shows when classical vision is enough. This course is for when it is not.
Is the course really free?
Yes. Every module, practice task, project and assessment. You create an account so your progress is saved and the assessments can be marked. The certificate is the only paid item, and only if you want it.
What certificate do I get?
An EDWartens Certificate of Completion, issued when you have submitted a project and passed the final assessment, with a verification code anyone can check. It is not a vendor credential and is never described as one.
Who made the video lessons?
The creators named in the Credits block at the foot of this page, on their own YouTube channels. EDWartens did not make the videos and the creators are not affiliated with EDWartens. What EDWartens wrote is the study plan, the notes, the practice tasks, the projects and the assessments.
What you walk away with
Your certificate for Deep Learning with TensorFlow and Keras
Finish the course, pass the final, and this is the document with your name on it.
Verifiable by anyone
A unique certificate number and a public verification page. A recruiter checks it in ten seconds.
Adds to LinkedIn in one click
Issuer, credential ID and URL prefilled, with 5 matching skills to pin to your profile.
QR code on the certificate
Scans straight to the verification page, so a printed copy proves itself.
Names what you can do
Lists the topics covered, from neurons, layers, activation, loss and gradient descent to a surface-defect classifier trained on colab gpu.
A permanent link
Put it on a CV, a portfolio or an application. The URL never changes.
Earned, not attended
Issued only after every module and a final assessment at 70%, with three attempts. That is why it stands up.
Learning is free. The certificate is optional.
Add it now and pay only when you have finished the course, or come back for it later. One-off, ₹559, GST included, with a receipt.
Issued by EDWartens India (Wartens Automation Private Limited) as a Certificate of Completion for this self-paced course. It is not a vendor certification, a university award or a CPD-accredited activity, and it does not certify competence on live equipment. Delivered electronically; see the refund policy.
Credits
Who made the video lessons
The video lessons in this course were created by the people below, not by EDWartens. Every lesson streams from its creator's own YouTube channel; EDWartens neither hosts nor sells that footage, and the creators are not affiliated with EDWartens and do not endorse this course. What EDWartens wrote is the study plan, the notes, the practice tasks and the assessments.
- codebasicsthe Deep Learning with TensorFlow 2.0, Keras and Python series
- freeCodeCamp.orgthe TensorFlow 2.0 complete course and the deep-learning crash course
- Edje Electronicsrunning TensorFlow Lite on a Raspberry Pi
If you are one of these creators and would like a lesson removed or credited differently, write to info@wartens.com.